© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127836
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literal tokens (numbers) in code.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    css style, env variable, related_name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     πάν
    -0.81
     this
    -0.81
     until
    -0.79
    ecke
    -0.77
     __(
    -0.76
    esti
    -0.76
     Until
    -0.76
    after
    -0.75
    】【
    -0.75
     进
    -0.75
    POSITIVE LOGITS
    Eid
    0.91
     étages
    0.84
    绿
    0.82
    Vikings
    0.81
    breitung
    0.79
    Cognitive
    0.79
    SNOW
    0.77
    FEBRUARY
    0.77
     sauter
    0.77
    asteroid
    0.76
    Activations Density 0.060%

    No Known Activations